Models & APIs

Higgsfield DoP Standard image-to-video (5s).

Higgsfield DoP Turbo image-to-video (5s).

Higgsfield Soul flagship text-to-image generation.

Create a fresh remote Chromium session with CDP and interactive live view.

Image to Image: AI image generation model for creating visual content. Generate images from text prompts for design, marketing, and creative automation workflows.

Monthly search volume + CPC + competition from Bing Ads for up to 200 keywords per task.

Google Ads keyword ideas: related/expanded keywords with volume + CPC.

Monthly search volume + CPC + competition from Google Ads for up to 1000 keywords per task. Live mode (avg 7s).

Kling v2.1 Pro image-to-video.

Semantically related keywords with volume and difficulty.

Monthly search volume history (4+ years) for keywords.

Submit an Amazon ASIN product detail scrape task. Use task_get to fetch results.

Submit an Amazon Products SERP scrape task. Use task_get to fetch results. Up to 100 products per SERP.

Submit an Amazon Sellers (offer listings) scrape task.

Image to Video generation - Animates images into 5-second videos with optional audio

Structured content extraction: text, headings, links, images, schema.

Instant single-URL on-page audit: title/meta, headings, content stats, internal links, status code.

Google Lighthouse audit: performance, accessibility, best practices, SEO, PWA scores.

Search the web through the repository-owned Perplexity adapter.

Qwen 3.5 Plus — Alibaba's native vision-language Plus model featuring a hybrid architecture that fuses linear attention with sparse Mixture-of-Experts, delivering superior inference efficiency. Supports multimodal inputs including text, images, and video with advanced visual understanding and deep reasoning. Demonstrates a significant performance leap over Qwen 3 in both pure-text and multimodal tasks, matching current frontier models. Built-in support for function calling, structured output, web search, prefix completion, and prompt caching.

Upscale an image through the bounded Replicate Real-ESRGAN adapter.

Use retrieve-knowledge to extract and process document information for AI agents. Ideal for Claude Code automation, data extraction workflows, and intelligent document analysis tasks.

Seedance 2.0 — high-quality text/image/video-to-video generation at 480p / 720p / 1080p, up to 15 seconds. Asynchronous: pass {"async": true} for a 1-second submit + poll status.

Seedance 2.0 Fast — cost-effective variant, ~20% cheaper at equivalent parameters. 480p / 720p (no 1080p), up to 15 seconds.